| Upload Date | August 11 2024 08:40 PM |
| Views | 26 |
| AI Information | |
|---|---|
| Framework | Core ML |
| Backend | Neural Engine |
| Device | Apple A16 Bionic |
| System Information | |
|---|---|
| Operating System | iOS 17.5.1 |
| Model | iPhone 14 Pro |
| Model ID | iPhone15,2 |
| Motherboard | D73AP |
| CPU Information | |
|---|---|
| Name | Apple A16 Bionic |
| Topology | 1 Processor, 6 Cores |
| Identifier | ARM |
| Base Frequency | 3.46 GHz |
| Cluster 1 | 2 Cores |
| Cluster 2 | 4 Cores |
| Memory Information | |
|---|---|
| Size | 5.50 GB |
| Workload | Accuracy | Score | |
|---|---|---|---|
|
Image Classification (SP)
|
100% |
1224
227.6 IPS |
|
|
Image Classification (HP)
|
100% |
5730
1.07 KIPS |
|
|
Image Classification (Q)
|
99% |
6189
1.15 KIPS |
|
|
Image Segmentation (SP)
|
100% |
742
12.0 IPS |
|
|
Image Segmentation (HP)
|
100% |
5092
82.5 IPS |
|
|
Image Segmentation (Q)
|
100% |
5075
82.3 IPS |
|
|
Pose Estimation (SP)
|
100% |
6254
7.30 IPS |
|
|
Pose Estimation (HP)
|
100% |
81283
94.8 IPS |
|
|
Pose Estimation (Q)
|
94% |
86537
101.5 IPS |
|
|
Object Detection (SP)
|
100% |
1302
103.3 IPS |
|
|
Object Detection (HP)
|
100% |
7687
609.7 IPS |
|
|
Object Detection (Q)
|
93% |
8282
660.8 IPS |
|
|
Face Detection (SP)
|
100% |
2217
26.3 IPS |
|
|
Face Detection (HP)
|
100% |
10936
129.9 IPS |
|
|
Face Detection (Q)
|
100% |
13021
154.7 IPS |
|
|
Depth Estimation (SP)
|
100% |
4096
31.6 IPS |
|
|
Depth Estimation (HP)
|
99% |
40119
309.1 IPS |
|
|
Depth Estimation (Q)
|
97% |
46162
356.9 IPS |
|
|
Style Transfer (SP)
|
100% |
11097
14.3 IPS |
|
|
Style Transfer (HP)
|
100% |
122149
157.0 IPS |
|
|
Style Transfer (Q)
|
100% |
121893
156.7 IPS |
|
|
Image Super-Resolution (SP)
|
100% |
3218
118.8 IPS |
|
|
Image Super-Resolution (HP)
|
100% |
16901
624.1 IPS |
|
|
Image Super-Resolution (Q)
|
98% |
21103
781.8 IPS |
|
|
Text Classification (SP)
|
100% |
1385
1.85 KIPS |
|
|
Text Classification (HP)
|
100% |
3070
4.10 KIPS |
|
|
Text Classification (Q)
|
93% |
2983
4.00 KIPS |
|
|
Machine Translation (SP)
|
100% |
1653
28.5 IPS |
|
|
Machine Translation (HP)
|
100% |
2319
39.9 IPS |
|
|
Machine Translation (Q)
|
98% |
2306
39.8 IPS |